Intelligent Conversation Control in Wearable Audio Systems

1. An apparatus comprising: a set of headphones having a right headphone and a left headphone; a microphone; a motion sensor positioned in one of the right or left headphone; and a processor configured to receive audio signals output by the microphone and motion data output by the motion sensor, the processor configured to: based on the motion data, determine whether the wearer's head is rotated to the right, left, or center, during an instance of the user speaking; based on the determination, select a first one of at least two audio signal destinations, and provide the audio signal from at least one of the microphones to the first selected audio signal destination.

2. The apparatus of claim 1 , wherein: each of the audio signal destinations comprises one of a voice user interface (VUI), a virtual personal assistant (VPA), a speech to text (STT) system, a live voice call, a voice recording system, or a voice messaging system.

3. The apparatus of claim 1 , wherein the processor is further configured to: continue to receive updated motion data from the motion sensor; based on the updated motion data, determine that the user's head is rotated to a different one of left, right, or center than was previously determined; based on the new determination, select a second one of the audio signal destinations, stop providing the audio signal from the microphone to the first selected audio signal destination, and start providing the audio signal from the microphone to the second selected audio signal destination.

4. The apparatus of claim 3 , wherein the earphones further comprise speakers, and wherein the processor is further configured to: while the user is facing in the first determined direction, provide audio received from the first selected audio signal destination to the speakers; and when the user changes to the second determined direction, decrease the level of the audio provided form the first selected audio signal destination to the speakers.

5. The apparatus of claim 3 , wherein the speakers comprise first and second speakers associated with the left and right earphones respectively, and wherein the processor is further configured to: while the user is facing in the first determined direction, provide audio received from the first selected audio signal destination to both of the speakers; and when the user changes to the second determined direction, provide audio received from the second selected audio signal destination to only one of the left or right earphone speakers, the selected earphone corresponding to the second determined direction.

6. The apparatus of claim 5 , wherein the processor is further configured to: while the user is facing the second direction, provide audio received from the first selected audio signal destination to both of the speakers at a decreased level than was used when the user was facing the first direction.

7. An apparatus comprising: a wearable audio device; a first microphone; a sensor for determining a direction in which the wearer of the wearable audio device is looking; and a processor configured to receive audio signals output by the microphone and look-direction data output by the sensor, the processor configured to: based on the look-direction data, determine whether the wearer's head is rotated to the right, left, or center, during an instance of the user speaking; based on the determination, provide the audio signal from the microphone to a voice personal assistant (VPA) only when the user is looking in a preconfigured one of right, left, or center.

8. The apparatus of claim 7 , wherein the wearable audio device comprises: a housing configured to rest on a wearer's neck or shoulders; the first microphone, positioned at a first position on the housing located on the right side of the wearer, when the housing is worn; and a second microphone positioned at a second position on the housing located on the left side of the wearer, when the housing is worn; wherein a processor configured; the sensor comprises the first and second microphones, and the processor is configured to: receive audio signals output by the first and second microphones, and implement the sensor to determine the direction in which the wearer of the wearable audio device is looking by: comparing the audio signals from the first microphone to the audio signals from the second microphone, and based on the comparison, determine whether the wearer's head is rotated to the right, left, or center.

9. The apparatus of claim 7 , wherein the wearable audio device comprises: a set of headphones having a right headphone and a left headphone; and a motion sensor positioned in one of the right or left headphone.

10. The apparatus of claim 7 , wherein the processor is further configured to: when the user is looking in a preconfigured second one of right, left, or center, convert the audio signal from the microphone to text, and transmit the text to a recipient.

11. The apparatus of claim 10 , wherein the processor is configured to determine the recipient based on content of the audio signal.

12. The apparatus of claim 10 , wherein the processor is configured to determine the recipient based on the direction in which the user is looking.